Year: 2025
Type: article
Abstract: With the exponential increase in digital documents, queries and extraction of information from PDFs in an intuitive manner have become highly required. This paper is a first-of-its-kind PDF Chat App that leverages LangChain and the Large Language Models of OpenAI to facilitate the real-time interaction of users with PDF content. The system applies NLP to enable conversational engagement involving interactive extraction of relevant portions, summaries, or answers of PDFs. The proposed framework sheds light on the challenges and limitations of these current solutions and presents an improved architecture using Retrieval-Augmented Generation.
Authors: Kotoju Rajitha, Md Aqdas, Molugu Aishwarya
Institution: Mahatma Gandhi Institute of Technology
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410031455